M01: Lecture Notes
Introduction to Generative AI & Business Applications
M01:
Notes
Lecture
Lecture covering Introduction to Generative AI & Business Applications.
0.1 Welcome to Applied Generative AI for Business Analytics (AD698)
1 Your Instructor
1.1 Nakul R. Padalkar
1.2 AD698 – Learning Path

2 What This Course Is About
This course explores how modern generative AI systems reshape analytical workflows and business decision-making. You will learn:
- How natural language functions as a data type
- How LLMs process text, structure information, and generate content
- How GenAI integrates with business analytics pipelines
- How to build practical generative-AI solutions with Python, APIs, and automation
- How to critically evaluate model outputs, reliability, and risks
- How to design human–AI workflows and deploy GenAI tools effectively in organizations
3 Why This Course Matters for Your Career
- Every analytics job now intersects with LLMs.
- Analysts who master prompt engineering, RAG, automation, and LLM-based workflows will dramatically outperform peers.
- AI-augmented analysts produce more work, more insight, and higher-value deliverables.
- Organizations expect you to understand:
- How AI reads and structures unstructured data
- How to integrate AI into dashboards, apps, and analytical workflows
- Responsible use, privacy, transparency, and governance principles
- This course trains you in supporting interviews, project pitches, and job applications while responding to the AI Augmented Analyst roles.
4 Course Overview

5 Course Structure
5.0.1 Modules 0–7
Each module has two lectures, one lab, and one assignment. Topics include:
- Introduction to LLMs and Natural Language
- Prompt Engineering & In-Context Learning
- Vector Search & RAG Systems
- AI-Driven Data Analytics
- Automation, Agents & Workflows
- Generative AI APIs for Business
- Evaluation, Safety, and Governance
- Deployment, Documentation & Portfolio
6 Course Grading
| Class Activity | Count | Points | Max Points |
|---|---|---|---|
| AWS Academy Generative AI Foundations | 1 | 100 | 100 |
| Github+githubpages ePortfolio Creation | 1 | 40 | 40 |
| Labs* | 10 | 20 | 200 |
| Assignment | 5 | 50 | 250 |
| Managerial report with Application Demo | 1 | 80 | 80 |
| Git and git website setup | 1 | - | - |
| Api and data gathering | 1 | - | - |
| Data cleaning and EDA | 1 | - | - |
| Analytics, including full website | 1 | - | - |
| Group Project Presentation | 1 | 40 | 40 |
| Group Feedback | 1 | 40 | 40 |
| Total | - | - | 750 |
7 Participation Components
7.0.1 LLM Lab Practice
- Weekly hands-on exercises using LLMs
- Focus on prompting, automation, and applied business tasks
7.0.2 Tooling: GitHub, Python, APIs
- You will maintain a public portfolio repository
- Every assignment and project will be submitted via GitHub
8 GitHub Repository & Portfolio
Lectures 0.1–0.3 walk through:
- Setting up GitHub
- Creating a portfolio site
- Connecting your work to Classroom
This repo will store:
- Lab notebooks
- Assignments
- Code files
- Project site generated with Quarto

9 In-Class Labs
Labs are short, guided activities where you:
- Work directly with LLM models
- Explore generative workflows
- Build first-draft AI tools that feed into assignments
- Analyze data, automate tasks, and generate outputs
- Write practical reports and visualizations
On-campus: must submit weekly Online: optional but recommended for practice
10 Individual Assignments
Four structured assignments that build core competencies:
- Prompt Engineering & Automated Analytics
- RAG and Vector Search
- AI Pipeline for Business Intelligence
- Automated Workflow + API Integration
11 Group Project
A semester-long generative-AI solution to a business problem.
11.0.1 Components
| Component | Points | Description |
|---|---|---|
| Milestones via GitHub | 80 | Repo setup, design docs, data prep, RAG prototype, LLM workflow, final output |
| Presentation | 40 | Demonstrates model workflow and business impact |
| Peer Evaluation | 40 | Collaboration, clarity, and contributions |
Total: 160 points
12 Course Site
- Central hub for all materials
- Contains lecture notes, slides, labs, and links
- Includes schedule, deadlines, and announcements
- Updated continuously as the course progresses

13 Office Hours & Consultations
- Listed on Blackboard
- Weekly sessions for troubleshooting code, labs, and assignments
- Dedicated project support sessions (Saturday mornings on Zoom)
14 Next: Lecture 1 — Natural Language & the Generative AI Landscape
Where we cover:
- What natural language actually is as a data type
- How LLMs encode and interpret language
- Embeddings, tokens, and structure
- The evolution of modern generative AI systems
- Business use-cases and early applications